https://www.youtube.com/live/C_f8pa9XhqM
It was a pretty interesting story, so I’ll pick up the transcript and comments later.
This was the first terrestrial broadlisting project that was delivered in retrospect. Main content:.
Project Summary
- Collaborating with Nippon Television Network Corporation to utilize broad listening technology for election coverage of the House of Representatives elections
- Analyzes comments on X (formerly Twitter) to visualize opinions about the election
- Produce all four types of reports (overall election, policy, each party, and same-day preliminary report)
Technical Challenges and Improvements
- TTTC system improvements (UI improvements, faster processing speed, etc.)
- Spam filtering implementation
- Addition of a favorites function
- Implementation of smartphone support
Main Results
- Utilize both terrestrial and digital distribution
- Six digital programs, six hours of live broadcast on election day
- Real-time public opinion analysis and visualization
Challenges and Learning
- Ensuring Accuracy (Importance of Fact Checking)
- Support for large-scale data processing
- Cooperation with broadcasters
Future Outlook
- Improved clustering methods
- Fact-checking automation study
- Possibility of utilizing a wider range of data sources
All participants appreciated that the project was an important step in the convergence of the broadcasting industry and technology.
2024-10-26
nishio Broad listening on TV show! Widely heard on TV programs!
nishio Nippon TV’s “news zero” is rolling out the innovative “Broad Listening” project, led by AI engineer Takahiro Anno, just in time for Japan’s House of Representatives election. NTV’s “news zero” is rolling out its innovative “Broad Listening” project, led by AI engineer Takahiro Anno, just in time for the House of Representatives election.
nishio With AI-driven analysis, Broad Listening visualizes over 38,000 election-related posts from X/Twitter, clustering similar opinions to highlight key voter discussions on policy, candidates, and social issues. (using “Talk to the City” tool by AI Objectives Institute ) Broad Listening uses AI-powered analysis to visualize over 38,000 election-related posts from X/Twitter, clustering similar opinions and highlighting key voter arguments about policy, candidates, and social issues. (Using AI Objectives Institute’s “Talk to the City” tool)
nishio This approach breaks filter bubbles, helping both the public and politicians see a broader view of opinions—including those often overlooked. Detail is on Nippon TV’s site: This approach breaks the filter bubble and helps both the public and politicians see opinions in a broader perspective, including those that are often overlooked. For more information, please visit NTV’s website.
nishio Anno team just released an enhanced version of “Talk to the City,” for their recent TV broadcasting program. They improved features like the favorites function, mobile-friendly UI, and cluster comment accuracy.
Right side is the favorite pane. The Anno team has released an enhanced version of “Talk to the City” for a recent TV broadcast program. Features such as favorites, mobile-friendly UI, and cluster commenting accuracy have been improved.
On the right is my favorite pane.
nishio Here is the Anno team’s Blog: Click here to read the Anno team’s blog.
You are a professional writer. I am thinking of writing an article in English to share this Japanese case study with people around the world who are interested in digital democracy. Please draft the article in Japanese first.
Japan’s terrestrial broadcasters have demonstrated a new challenge to the digitalization of democracy.
A Breakthrough in Election Reporting x Collective Intelligence Analysis.
Introduction.
NTV, a major commercial TV station, has implemented a groundbreaking initiative for Japan’s 2024 House of Representatives election. The project combines conventional election reporting with the latest AI technology to visualize the voices of voters on social media in real time. This attempt offers new insights into the nature of democracy in the digital age.
Project Innovation
The project is notable for its attempt by traditional media to leverage the “collective intelligence” of the digital space. Specifically, election-related posts on social media X (formerly Twitter) were analyzed in real time using AI technology. The results were provided to viewers through both terrestrial broadcasting and digital distribution.
Technical Features
The core technology is a technique known as “broadcast listening. This is the opposite concept of “broadcast (one-to-many information dissemination),” in which the opinions of many people are aggregated and presented in an organized form. It is based on the open source software “talk to the city” and has been realized with unique improvements.
Implementation and Results The project conducted the following four types of analysis
Public opinion on the election as a whole Trends in Policy Discussion Responses to each political party Real-time reactions during the vote count
Particularly noteworthy was the effort on the day of the vote count. In just 25 minutes after the polls opened, 60,000 submissions were collected and analyzed, and the results of the analysis were successfully provided to viewers 85 minutes later. This demonstrated the potential for highly immediate election coverage in the digital age. Challenges and Prospects The project also identified several important issues:
Representativeness of opinions on digital platforms Need for automated fact-checking Data quality control and privacy protection
At the same time, however, these challenges are important considerations in the future development of digital democracy. Conclusion. This attempt deserves attention as an example of how the fusion of traditional media and digital technology opens up new possibilities for democracy. In particular, the effort to visualize voters’ voices in real time will serve as a model case for future digitalization of election coverage and democracy.
TV Broadcasting x AI: An Experiment in Democratic Digitization from Japan ～Behind the Scenes of the World’s First AI-Based Election Reporting by a Terrestrial TV Station summary During Japan’s October 2024 lower house election, NTV, a major Japanese broadcaster, implemented a groundbreaking AI-based election coverage project. Called “Broad Listening,” the technology analyzed and visualized tens of thousands of posts on social media in real time. Technical characteristics of the project Data collection and analysis systems
Analysis of: election-related posts on X (formerly Twitter) Collection size: 1 million posts (budget: approximately $5,000) Analysis period: 3 periods: pre-election period, first half, and second half Real-time analysis: 60,000 cases processed in 25 minutes on the day of the vote count
Analysis Category
Overall Election Trend Analysis Trend Analysis of Policy Discussion Reaction analysis by political party Real-time analysis during preliminary vote counting
Technical improvements
UI/UX Improvements
Implementation of a favorites function Smartphone and tablet support Optimization of visibility for broadcast
Improvement of analysis accuracy
Improved clustering algorithm Optimization of the method for extracting representative comments Spam filtering implementation
Important Points for Implementation system requirement
Tier 5 level processing power of GPT API Stable processing up to 200 parallels Support for 7-day data acquisition limit Establishment of 24-hour operation system
Quality Control Process
Primary filtering by AI Manual fact-checking Processing into broadcast content Final confirmation process
Operation System
Engineering Team: System Development and Maintenance Editorial Team: Content Creation Broadcast station team: Quality control and broadcast support Project management: Daily progress review meetings
Findings technical side
Importance of using and improving open source software Effects of Parallelization in Real-Time Processing Need for continuous improvement of UI/UX
practical side
Importance of close cooperation with broadcasters Establishment of fact-checking system Maintain flexible improvement cycles
Future Outlook
Further improvement of clustering methods Consideration of fact-checking automation Possibility of multi-platform support
Conclusion. This project was an important practical example of the integration of conventional media and AI technology. In particular, the fact that the project was based on open source software that was modified for actual broadcasting applications will serve as a valuable reference case for similar projects in the future.
Schedule to be on TV until 26:00 and then immediately to the US the next morning.
This page is auto-translated from /nishio/ブロードリスニングでの衆院選解析を振り返る using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.